Rules

what constrains decisions

Nothing matches the filter.

• booping:rule/0001A lesson is a ruleacceptednot acceptedWhat a run teaches is recorded as a rule with targets and a brief; only the brief reaches the targeted step, the body is read on demand.
• booping:rule/0004Open questions are settled in grooming, not in developacceptednot acceptedGrooming hunts for open questions and settles them with the user before ready-for-dev; develop stops only for force majeure.
• booping:rule/0006Every prompt artefact passes the information-architecture checkacceptednot acceptedBefore a prompt-bearing artefact is saved, every block passes four checks — scoping, duplication, configurability, hierarchy — and prose that only restates or motivates is cut.
• booping:rule/0007References a plan invalidates are cleaned up in the same sprintacceptednot acceptedWhen a plan deletes or renames something others reference, the cleanup is a milestone task of the same sprint with its own DoD, never a follow-up sweep.
• booping:rule/0008Generated content is scoped to its audienceacceptednot acceptedUser-facing output — release notes, user docs, changelogs — includes only what that audience touches; the audience filter is specced into the task's DoD.
• booping:rule/0009An agent briefing bounds what the agent returnsacceptednot acceptedEvery agent briefing states the exact shape of the agent's reply, limited to what the orchestrator needs; groom bounds it in the task so develop's briefings inherit it.
• booping:rule/0010The content of a user-facing output is locked in groomingacceptednot acceptedWhen a plan defines a user-facing output or log format, its exact content — fields, truncation, trailers — is settled with the user in grooming, not iterated in develop.
• booping:rule/0030Planning shows the values in play and every departure from themacceptednot acceptedA plan names the values that drive its choices and flags where it departs from a value or rule, so the user sees what works and can refine the values.
• booping:rule/0031Corrections are logged as they happenacceptednot acceptedWhen the user corrects the driver, it logs the correction verbatim as a file under the vault's corrections/, so retro starts from a ready list of what is not yet handled.
• booping:rule/0032Decisions are asked in proseacceptednot acceptedAn approval, or any decision the user must understand the context to make, is asked in prose, one at a time with compact context and a counter; a multiple-choice tool only for mechanical picks.
• booping:rule/0033Decisions are listed for acceptanceacceptednot acceptedBefore the user accepts anything, the agent lists every decision it takes as settled, one numbered line each, marking its own proposals; an unanswered item is never accepted.
• booping:rule/0034A specs review tests each record against its typeacceptednot acceptedA review of the specs puts every record to the type tests of the format guide and lists each failure — the type it fits or deletion — for the user to accept.
• booping:rule/0035Items of one class are groomed together, never in parallelacceptednot acceptedThe manager grooms items of the same class in one plan, or one after another with the earlier plan in the next brief — never in parallel, where each builds its own copy of the mechanism.
• booping:rule/0036An ADR is accepted after a briefacceptednot acceptedAn ADR is drafted proposed and accepted only after the owner was shown its brief and given a window to object; the answer sets the review level with its evidence.
• booping:rule/0037Open items hold only what outlives the sessionacceptednot acceptedAn open item is filed only for work for later or a question that waits for the owner; session instructions, gate answers, policies and decisions are never items.
• booping:rule/0038Ids in chat carry their titleacceptednot acceptedEvery id said in chat — an open item, an ADR, a rule, a plan — is followed by its short title; newly filed items are listed one per line with their title.
• booping:rule/0039Experiments run in stagesacceptednot acceptedAn experiment, eval or benchmark matrix runs a cheap screen, then a shortlist, then significance for finalists only, each stage sized before launch.
• booping:rule/0040The ADR scorer judges its prompt aloneacceptednot acceptedThe adr-scorer runs only its body render and judges a draft ADR from the pasted parts alone; nothing it was not shown exists for it.
• booping:rule/0041The manager delegates heavy readsacceptedThe project manager never reviews an artefact, reads a long file or scans many files or logs itself; a subagent does it under a bounded return contract and the manager keeps only the verdict.